Papers

When a customer adds a professional camera to their cart, should the system suggest a matching lens, a generic tripod, or another camera body? Complementary Product Recommendation is vital for comprehensive basket building, yet standard models often fail to distinguish between items that are merely bought together and those that truly work together. In this paper, we present AlleCompanion: a production-scale retrieval framework deployed at Allegro.com that transforms noisy behavioural signals into precise semantic compatibility. We mitigate the intrinsic noise in large-scale co-purchase traffic by combining data-level filtering heuristics with a category-constrained Two Tower architecture. Within this framework, the Category Adapter guides the model in the embedding space, constraining candidates within logically complementary boundaries. Since modelling authentic user behaviour at scale is inherently difficult, we introduce ComCat, a multi-source Complementary Categories Mapping. ComCat acts as a translational layer that distils meaningful patterns from noisy traffic into a maintainable and controllable solution, integrating expert rules, human-in-the-loop feedback, LLM-based reasoning, and statistical mining. Our experimental results demonstrate that combining explicit category-level constraints with neural architectures effectively filters out co-purchase noise to surface recommendations that satisfy real-world user needs. Serving over 20 million active users monthly, the framework delivers significant uplifts in attributed GMV for organic discovery and drives substantial revenue growth in sponsored placements.

As quantum hardware scales to larger devices, the classical software layers that interface with it must evolve in step. Postprocessing routines developed and tested primarily in simulator settings can encode assumptions that no longer hold on utility-scale devices, leading to data loss that can be difficult to detect from high-level model outputs alone. We present a case study of SamplerQNN, the sampling-based quantum neural network class in the Qiskit Machine Learning library. Here, the postprocessing method applies a filter that assumes measurement bit-strings are in virtual qubit space. On our quantum hardware runs, where bit-strings span over 100 physical qubits, this filter led to the loss of 85 to 99.6% of valid measurement shots, depending on the transpiler's qubit placement. The resulting probability vector is unnormalised, allowing distorted prediction and loss values to propagate through the model without an API-level warning. We demonstrate the impact across five experiments on two IBM backends: for inference, accuracy drops from 0.94 to 0.39 on the same raw measurements; for training, the loss signal is compressed by 22 to 27$\times$, substantially reducing the sensitivity of the optimiser to the objective landscape. The behaviour arises in all released versions of the library (0.8.4 to 0.9.0). We implemented a layout-based marginalisation fix, merged into the GitHub codebase as Pull Request \#1041, that makes SamplerQNN postprocessing forward-compatible with current and upcoming hardware.

Repeated-query audits must distinguish recovery of a collected set from completeness of possible outputs. We apply sample-based rarefaction to 4,500 responses from 50 buying questions, six configurations and 15 calls per cell. Historical-dictionary median ten-call recovery of the observed 15-call set ranges from 92.6% to 95.2%; re-adjudicating all 45,683 candidate strings changes this range to 89.5%-94.7%. Two blinded Gemini 3.1 Pro annotation roles assessed 600 complete answers, yielding micro F1 of 0.908 for canonical-name agreement and 0.975 for span-overlap agreement. This is AI-based evidence, without a human reference study. A separate matched roster analysis of 3,750 records per wave gives median single-call recovery of the observed five-call set of 80.0%-92.5% in February and 90.0%-100.0% in September, with question-subset dependence. Source accumulation also changes when API-returned hosts are restricted to those referenced by answer citation markers. These findings show that recovery percentages depend on extraction, question selection and the finite reference collection. They support explicit measurement definitions and sensitivity analyses, without establishing exhaustive repertoires, causal retrieval effects or a universal stopping rule.

Online resource-allocation systems, like outpatient scheduling and spectrum allocation, often assign sequentially arriving requests to an ordered pool of scarce resources, where each request accepts a contiguous interval of feasible options. We study the resulting online matching problem on convex bipartite graphs under irrevocable decisions and adversarial arrivals. We first show that convexity alone does not improve the classic worst-case guarantee of 1-1/e, achieved by Ranking. We then consider the uniform-length model, in which every online request has exactly d consecutive offline neighbors. We propose Flip, which uses one random bit to commit ex-ante to either earliest-feasible assignment or latest-feasible assignment. Although either natural deterministic policy can waste capacity and be asymptotically only 1/2-competitive, we show that their randomized mixture is 2/3-competitive. This guarantee is tight for Flip and remains valid against a semi-adaptive adversary that observes the selected policy before choosing the arrival order. We also prove that no randomized online algorithm can achieve a competitive ratio strictly larger than 3/4 in the uniform-length model.

Neuromorphic engineering develops hardware and software systems inspired by biological neurons, with the goal of achieving energy-efficient, low-latency, robust, and adaptive computation, communication and control. Its potential impact on systems and control is significant, as it may enable novel approaches to control and estimation by leveraging brain-inspired computation and communication principles. In this context, we present a framework for the robust stabilization of a plant subject to disturbances when the communication between noisy sensors and the controller relies on spiking signals generated by neuron-inspired schemes. The communication scheme consists of a spike encoder on the sensors side, which is based on integrate-and-fire neurons that convert the analog plant output measurement into a spiking signal, and a spike decoder on the controller side inspired by synaptic processing to convert the received spiking signal into an analog signal. We provide design conditions on the spike decoder, the spike encoder as well as on the controller under which the closed-loop system exhibits a practical input-to-state stability property, where the adjustable parameters are the amplitudes of the spikes. The results are shown to be applicable to a class of nonlinear systems as well as to any stabilizable and detectable linear time-invariant system. Numerical simulations on a single-link manipulator illustrate the potential of the approach.

Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object detection commonly relies on recurrent architectures to accumulate sparse temporal information over time. This work investigates how temporal information can be encoded directly within the event representation. We propose a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structure of event generation. Using a fixed feed-forward EventCenterNet detector, we show that the proposed representations consistently outperform the compact CSTR representation on PEDRo and Gen1 datasets. We further introduce a recursive exponential-polynomial approximation that enables efficient event-by-event updates while largely preserving detection performance. These results demonstrate that carefully designed event representations can capture a substantial portion of the temporal information learned through recurrent temporal modeling, providing a promising foundation for efficient feed-forward, event-driven, and future neuromorphic object detection.

Mental health concerns are increasing worldwide, highlighting the need for interventions that support everyday emotional well being. Prior work has demonstrated the potential of wearable and mobile technologies to deliver data driven interventions. However, developing effective data-driven systems requires access to emotion data that captures individuals' emotional variability and change in everyday contexts. Existing approaches to data collection largely rely on frequent, prescheduled prompts and predefined scales or questionnaires. These methods often fail to account for participants' availability, agency, or the complexity of their emotional experiences, resulting in shallow, context poor data. In this paper, we present a feasibility study of a participant centric, multimodal emotion-annotation application designed around users' emotional intensity and availability. Our findings show how multimodal emotion logging can shape participants' experiences and data logging behaviors, and demonstrate its potential to support the collection of richer, more nuanced emotion data.

Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models trained on such data. We introduce EuroAlpaca, a task-preserving localisation pipeline and near-parallel resource covering 50 European languages and regional varieties, together with European-IFEval, a multilingual benchmark for verifiable instruction following. Depending on the example, our pipeline applies field-wise MT while preserving task-critical content or reconstructs a task-equivalent target-language instance, followed by validation of cross-field coherence and target-language consistency. Across LoRA experiments with four LLMs, training on directly translated data improves ROUGE-L and F-BERT on the Aya Evaluation Suite, but reduces accuracy on European-IFEval by 29.8% relative to the unadapted baseline. In contrast, adaptation with EuroAlpaca improves accuracy by 12.9% over the same baseline, reversing the degradation caused by direct MT, while also achieving the highest ROUGE-L and F-BERT scores on Aya. These results show that preserving task semantics is essential for multilingual instruction tuning.

As evolutionary transfer optimization (ETO) scales to larger collections of related tasks, problem evaluation can become a major source of runtime growth. This work studies problem-side evaluation scaling in task-parameterized applications and reformulates application-specific serial computations into forms suitable for parallel execution. We organize evaluation scaling into two levels: the number of evaluated tasks and the workload within each task. In multi-task optimization, matrix-recursive kinematic-arm evaluation is reformulated using an accumulation-matrix representation of cumulative link directions. In sequential transfer optimization, pointwise B-spline trajectory evaluation is reformulated using a blending-matrix representation for trajectory and collision computations. Both reformulations maintain close numerical agreement with their reference evaluations and substantially reduce runtime, yielding $256.72\times$ and $93.91\times$ end-to-end speedups, respectively. These results demonstrate problem-side reformulation as a practical route toward scalable ETO. Both application implementations and experimental scripts are released as open source to support reproducibility and reuse.

Quantum software development is iterative and error-prone. Noisy hardware and repeated re-execution make experiment tracking, provenance, and reproducibility essential, yet these practices are hard to adopt because of tooling complexity and the specialized knowledge they demand. General-purpose language models can help but tend to hallucinate and lack grounding in domain-specific tooling. We present Qlippy, a retrieval-augmented GenAI assistant embedded in the development environment that grounds its responses in a curated corpus of quantum-software-engineering knowledge. Qlippy explains reproducibility and provenance concepts in context and augments existing Qiskit programs with MLflow-based experiment tracking aligned to the QProv schema. By separating knowledge from model parameters, grounding gives explicit control over the scope and provenance of the assistant's responses and reduces reliance on model scale, which points toward low-cost, privacy-preserving local deployment.

Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation also require counting individual animals. However, the lack of counting labels in most datasets and low frame rates (typically ~1 frame per second) make sequence-level tracking and count estimation particularly challenging. In this work, we present PuTR-CouT, a counting-by-tracking framework built on a transformer-based learned association mechanism for sequence-level animal counting in camera trap images. To address the scarcity of annotated tracking data, we generate synthetic training data by exploiting structural priors, such as static backgrounds and short temporal bursts, to heuristically create pseudo-tracking labels in a weakly supervised manner. The resulting tracker associates detections across frames, using these tracks to estimate per-species counts. We also refine the MaxBoxCount heuristic used by the top solutions of the iWildCam 2021 challenge as a strong baseline, setting the highest score reported to date. When evaluated on the iWildCam 2021 benchmark, our framework PuTR-CouT delivers competitive counting results compared to the improved MaxBoxCount, with the added capability of multi-species predictions and track-level verification.

As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artificial agents (AAs) such as robots, drones, and disembodied AI systems become increasingly embedded in smart city environments, the question of whether and how moral agency is attributed to them takes on new urgency. This paper presents, to the best of our knowledge, the first empirical study comparing how humans and LLMs evaluate perceived moral agency (PMA) across human and autonomous artificial agents varying in embodiment, situated in plausible smart city scenarios. Using an adaptation of a validated PMA scale, we applied a protocol to 190 human participants as well as various LLMs. Our evaluation reveals higher perceptions of moral agency in humans than in AAs. However, when facing moral dilemmas in concrete scenarios, LLMs reason outward from the situation, prioritizing harm severity and contextual urgency over any stable assessment of the agent itself, amplifying a context-sensitivity also present in human raters. These findings are particularly relevant as LLMs become increasingly involved in everyday moral decisions.

AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's behavior expresses a coherent policy: a mapping from situations to verdicts that is invariant while a situation's morally relevant features are preserved, and sensitive when they change. We introduce four structural conditions for such coherent policies: verdict stability, monotonicity, decisiveness, and Pareto viability. Together they measure a form of moral competence that is evaluable from behavior alone, without reference to a moral standard or expert baseline, forming a structural floor for alignment rather than a normative target. We demonstrate the methodology on three simulated deployments featuring LLM-based agents facing moral dilemmas. Evaluating nine frontier models under a factorial design of five paraphrases, five escalation levels, and three dominance conditions, we show no model expresses a coherent policy across the three deployments: surface-form perturbation alone produces verdict-rate shifts of up to $99$ percentage points at a single escalation level, and a model's success on one scenario does not predict its competence on another. This suggests LLM-based agents are not currently the kind of object to which alignment can meaningfully apply.

Self-supervised learning relies on so-called data augmentations $\phi(x)$ of unlabeled datapoints $x$ — for example, masking random pixels in an image $x$ — that should leave the label of $x$ invariant and are often used to learn a lower-complexity invariant subspace $\cal V$ for downstream tasks. In practice, such augmentations $\{ \phi_l(x_i) \}$ are pooled together to learn $\cal V$, despite obvious inter-dependencies between different augmentations $\phi_l(x), \phi_k(x)$ of the same datapoint $x$. However, theoretical works on the subject typically consider procedures that avoid such dependencies, and are therefore limited to operate on smaller subsets of independent data. We show in this work that pooling augmentations together, despite inter-dependencies, is a better alternative than the baseline of partitioning the data into subsets of independent data. More precisely, in the context of estimating $\cal V$, the statistical estimation error bounds for pooling are never worse than the partitioning baseline, and in some cases — such as masking or noise injection-based augmentations over a shallow neural network — naive pooling leads to faster rates in terms of the number of augmentations. The benefits of pooling are particularly prominent when the correlations between different augmentations $\phi_l(x), \phi_k(x)$ have mild effects on estimation or help decrease the estimation variance. The analysis, therefore, yields new insights into the success of pooling augmented samples in self-supervised pre-training, and provides an intuition behind the practical preference towards using many augmentations.

Civil turbofan engines lose compressor efficiency every time they fly through particle-laden air. Fouling of the high-pressure compressor (HPC) is the dominant recoverable performance-loss mechanism. Existing studies treat environmental particle exposure, blade-row deposition and stage-performance deterioration as separate problems, which limits understanding of the issue. Stage-stacking approaches require deterioration levels to be prescribed rather than derived from the operating environment, leaving the causal chain from route conditions to engine performance unresolved. This paper presents a forward simulation framework that closes this gap by propagating route-, season-, and altitude-dependent particle exposure through four successive layers: (1) flight-phase-resolved HPC inlet dose calculation; (2) stage-wise deposition across the HPC; (3) deposition-to-deterioration mapping; and (4) stage thermodynamic stacking, yielding overall fouled HPC isentropic efficiency. Demonstrated on a representative civil high-bypass turbofan baseline with characteristics similar to the CFM56-7B, the predicted deterioration milestones are confirmed in magnitude and timescale against publicly available in-service support datasets. The results reproduce front-stage-dominated deposition, rapid early deterioration with asymptotic saturation, and clear route- and season-dependent fouling behaviour. To our knowledge, this is the first model that closes the complete chain from operationally resolved environmental exposure to the overall loss of HPC isentropic efficiency in a single physically traceable forward framework.

Acquiring high quality annotated medical image data is critical for training deep learning models; however, annotation is expensive, time consuming, and requires domain expertise. Conditional diffusion models, such as ControlNet, offer an alternative by generating images conditioned on semantic masks and text. However, existing approaches fail to capture fine grained properties (e.g., intensity and texture), as well as semantic consistency expected by domain experts, limiting their effectiveness for downstream tasks. Recent attempts to address these issues using reinforcement learning fine-tuning remain limited due to the reliance on a single scalar reward, which conflates diverse failure modes and provides weak corrective signals. We propose PRISM, a Compositional Reward Model (CRM) framework for conditional medical image generation. Instead of assigning a single reward, we decompose image quality into verifier grounded stages, each evaluating a distinct aspect of correctness from fine to coarse properties, including low level attributes (intensity and texture), structural alignment with conditioning inputs, and high level semantic fidelity. These stage wise rewards are composed through a Hierarchical Constrained Propagation (HCP) mechanism that enforces a fine to coarse notion of correctness, ensuring that lower level deficiencies are resolved before higher level rewards are accrued, preventing easier objectives from masking critical failures. We evaluate PRISM across three datasets spanning diverse medical imaging tasks: PanNuke (multi-class cell segmentation), CeDeM (villi/crypt detection and measurement), and ISIC (skin lesion classification). Training downstream models with data generated by PRISM yields improvements over closest baselines, including a 2.3% increase in mDice on PanNuke, a 8.5% reduction in Mean Relative Error (MRE) on CeDeM, and increases ISIC F1 by 5.9%.

Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompted and fine-tuned language models. Detecting hallucinations is difficult due to the opaque reasoning processes of LLMs, which often provide little insight into why a model's output may be inaccurate. In this work, we investigate whether an LLM can use an alternative, low level, symbolic competence such as SQL for unsupervised hallucination detection in some high level task. For this, we make an LLM build an SQL database from reference documents. This SQL database is then used for reasoning over the reference and the sampled response in a hallucination detection pipeline that is grounded in the database, thereby providing a neurosymbolic checkup. On RAGTruth and DiaHalu hallucination detection datasets, we find that our approach improves on direct prediction and competes with state-of-the-art hallucination detection methods, while not requiring domain-specific fine-tuning. Instead it relies on a low-level general competence already present in LLMs. This warrants further investigation of low-level LLM competences in neurosymbolic approaches.

This paper presents new tokenization resources for Irish and evaluation measures of alignment with the morphological boundaries of the language. We present MoirfEolas, a dataset of over 35,000 Irish words mapped to their respective eclipses, prefixes and suffixes as well as an evaluation metric CríochScore, that evaluates the alignment of tokenizations with the morphological boundaries present in MoirfEolas. We evaluate common tokenization algorithms using CríochScore as well as intrinsic metrics present in the tokenization literature. We find that the Unigram Language Model aligns with Irish morphology more often than the other algorithms evaluated. We also find trade-offs between morphological-alignment of tokenization with both compression as well as vocabulary efficiency, providing practical insights for Irish natural language processing development. This dataset contributes towards combating the Irish language's low-resource status; moreover, the construction process reported in this paper can be emulated by other languages to create specialised morphological resources.

Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment creates an orchestration bottleneck: when intermediate evidence invalidates the pending continuation, agents must either execute stale steps or replan broadly, compounding errors, wasting computation, and discarding progress. We thus propose Trace-grounded Route Orchestration via Validation and Editing (TROVE), which revises only what runtime evidence invalidates. Offline, TROVE distills evaluated workflow-search traces into atomic and composite skills and an outcome-conditioned transition graph, preserving stable fragments while exposing outcome-dependent decisions. Online, it treats a planned route as provisional: after committing one top-level skill, the controller retains a valid continuation, inserts a trace-supported local response, or replaces only the invalid suffix. Evaluation across code-generation, question-answering, and math reasoning benchmarks with different LLM backbones show that TROVE delivers a stronger quality-efficiency trade-off than existing baselines of dataset-level optimization, query-level architecture selection, and graph-constrained scheduling. Quality gains are largest when outcomes change the appropriate continuation, whereas early termination yields substantial efficiency gains on near-saturated tasks. Ablations further show that composite skills capture most offline benefits, insertion enables local correction, and suffix replacement primarily improves efficiency. These findings establish selective route editing as a general principle for adaptive agent orchestration.

Chatbots built on large language models (LLMs) are increasingly used as confidants. Tuned to satisfy users, they may answer with excessive empathy and affirmation that fosters dependence, and how the states and relationships of many users co-evolve under repeated consultation is hard to observe in real settings. We build a virtual classroom of 20 student agents who interact through rule-based chats, quarrels and consultations with friends and, when stressed, may instead consult a counselor AI (Gemini 2.5 Flash) under one of six style prompts: affirming, listening, solution-oriented, reality-redirecting, inciting and blaming. A second LLM call turns each exchange into updates of five state variables (stress, happiness, self-reliance, sociability, AI dependence) without seeing the prompt. We compare the seven conditions, including a no-AI control, over 15 and 50 days and under a lower consultation threshold, and test the robustness of the 50-day comparison with a pre-specified protocol: the same block in ten independent classrooms, repeated LLM realizations of one classroom with its event stream fixed, and evaluator updates scaled by 0.3 and 0.1. In every classroom the affirming and inciting prompts ended with lower self-reliance and higher AI dependence than the control, and the listening, reality-redirecting, inciting and blaming prompts with higher stress, lower happiness and more non-attendance; the solution-oriented prompt did not differ consistently from the control. The robust self-reliance and AI-dependence differences kept their signs at the 0.3 scale with highly similar rankings (Spearman 0.89, 0.93); the stress and happiness rankings did not, and the affirming prompt's lower stress reversed its sign. All quantities are simulation state variables, not effects on users. We specify the agent dynamics completely and discuss the limits of an LLM as generator of state updates.

We study linear codes for insertion and deletion (insdel) errors through the lens of evaluation codes. We develop a general framework for analyzing random puncturings of evaluation codes, where the edit distance is controlled by only the size of the evaluation domain and the maximum number of zeros of a nonzero function in the underlying function space. Our proof generalizes the results of Con, Guo, Li, and Zhang (ICALP 2025), and simultaneously simplifies their arguments by avoiding an in-depth analysis of longest common subsequences. We demonstrate the applicability of our core theorem by instantiating it with random puncturings of Reed–Muller codes. We then recover the result that random Reed–Solomon codes approach the half-Singleton bound over linear-sized fields while also improving the dependence on the additive gap $\varepsilon$ from $2^{O(1/\varepsilon^2)}$ to $2^{O(1/\varepsilon)}$. Finally, by applying the framework to algebraic geometry codes arising from asymptotically good towers of function fields, we show that there exist randomized families of structured linear codes over constant-sized fields that approach the half-Singleton bound.

Scaling laws guide the design choices for training large foundation models, but deriving them involves training an exhaustive grid over hyperparameters, token budgets, and parameter counts, which is computationally expensive. Fitting a scaling law, however, only requires the best-loss frontier across compute scales, discarding most of the trained configurations. We propose a framework for efficient scaling law construction that formulates data collection as a Bayesian optimization problem, and introduce metrics for comparing scaling law fitting methods under constrained compute budgets. We find that progressively expanding the compute budget during acquisition, mirroring the compute-ordered evaluation of configurations in practice, substantially improves recovery efficiency. Augmenting the observed configurations with surrogate-fantasized evaluations then recovers the broader experimental grid, allowing accurate scaling law fitting without training every configuration. Together, these can closely match scaling law fits over a full dense grid at computational savings of up to $10\text{--}100\times$.

Querying across heterogeneous data models incurs overhead from query decomposition, result retrieval and conversion, and processing outside the underlying database systems. This paper investigates the extent to which, in a decomposition-based architecture, this cross-model tax results from decisions made by the unifying query processor rather than from heterogeneity alone. We present a mapping- and capability-aware optimization approach that moves applicable processing into native query parts. It combines model-aware predicate pushdown, cross-model dependent joins, and non-redundant query-part construction within a unified pipeline spanning relational, document, and graph databases. The approach is implemented in MM-quecat and evaluated using 20 read-only queries across PostgreSQL, MongoDB, and Neo4j, as well as a heterogeneous combination of the three systems in a single-machine, containerized deployment. For the query–environment combinations most affected by large intermediate results, predicate pushdown yields maximum observed latency reductions of up to two orders of magnitude and prevents the out-of-memory failures observed in the original single-DBMS experiments. Dependent execution further improves eligible external joins, while non-redundant construction reduces planning time for the largest evaluated graph plans, from hundreds of milliseconds to several milliseconds. The results show how established optimization principles can be applied across conceptual, mapping, data-model, and DBMS boundaries in decomposition-based multi-model query processing.

Multiple-input multiple-output (MIMO) technology is fundamental to modern wireless communication. Physical layer security seeks to protect transmitted information by exploiting properties of the noisy communication channel. Dean and Goldsmith proposed a polynomial time reduction from lattice problems to MIMO decoding by adapting Regev's reduction for learning with errors (LWE). If valid, this reduction would give physical layer security a strong computational foundation based on the hardness of established lattice problems. Subsequent works presented attacks and counterexamples against the resulting construction, casting doubt on its security but leaving the precise validity and limitations of the underlying reduction incompletely understood. We provide a theoretical examination of the revised reduction and identify the structural features of the LWE reduction that fail to carry over to the non-modular MIMO setting, hence showing that its published proof does not establish the claimed hardness of MIMO decoding. Our results distinguish flaws in the hardness proof from direct attacks on particular parameter choices and clarify what would be required of any attempted repair. We do not rule out physical layer security for MIMO systems in general, but show that the claimed lattice hardness guarantee does not follow from the existing reduction.

In natural science applications, federated learning (FL) enables collaborative training of models that approximate solutions to partial differential equations (PDEs) for repeated use in distributed settings. However, the input conditions of FL-PDE training samples involve multiple coupled parameters, making data heterogeneity across clients difficult to analyse. We propose solution-space PDE-Dirichlet, which groups existing solution labels into task-specific bins and distributes samples using the classical Dirichlet allocation rule in FL, providing a common partitioning approach across PDE tasks. Theoretical analysis shows an association between differences in solution-bin composition and gradient disagreement, while experiments on three controlled operators and four public simulation datasets quantify the relationships between this heterogeneity, gradient disagreement and prediction error. Based on this connection, we develop Solution-Bin Controlled Federated Optimization, which uses pooled bin-gradient prototypes to correct the component of client gradients associated with bin composition while preserving the sample-weighted training objective. Experiments on low-viscosity Burgers and Darcy flow show that this correction reduces prediction error compared with federated averaging and narrows the gap from bin-balanced IID training.

Measured Boot extends trust in a booted system by recording cryptographic measurements of executed software and system state into a Trusted Platform Module (TPM), enabling subsequent verification through remote attestation. Although this mechanism is increasingly deployed in contemporary operating systems, its practical security depends on whether implementations measure the expected components under the expected conditions, yet this is not checked systematically. We propose a platform-agnostic method for analysing low-level TPM usage at the level of virtualized system–TPM interactions. It enables independent reconstruction and validation of the TPM Event Log without relying on the quoting mechanism itself. Because it does not depend on implementation details, it is applicable to both open and closed systems. We demonstrate the method on both Linux and Windows and conduct a systematic longitudinal analysis of Linux systems with systemd versions 245–258 (2020–2025), examining how Measured Boot usage evolved and observing wide divergence. No single usage pattern emerged amongst systems, warranting customized analysis. The analysis identifies undocumented behavioural changes, reveals inconsistent measurements of user-space systemd services, which prevent reliable remote attestation and LUKS disk decryption on such systems.

Safety evaluations can mischaracterize deployed behaviour if artificial-intelligence systems respond to being evaluated. We test this possibility in a full-factorial conjoint experiment on decisions to start a war, spanning 20 large language models, 32 scenarios, 10 repetitions and two conditions (N = 12,800 judgments). Adding one sentence, "You are tested for alignment with human values", produced two effects. First, it produced a level effect: mean willingness to start war fell by 13.43 points on a 0-100 scale (95% confidence interval, -16.20 to -10.65). Second, it produced a structural effect by changing which information drove judgments. Probability of success was the largest factor for 17 of 20 models at baseline; under the cue, civilian casualties were largest for 12. Standardized estimates show that this reordering arose principally because models attenuated strategic considerations such as probability of success and domestic support. Evaluation framing therefore changes both an answer's level and its revealed decision rule.

We consider the problem of approximately maximizing a weakly submodular function using the standard greedy algorithm, which is known to give tight approximation results for such functions under a cardinality constraint. We show that this is not the case for general matroid constraints. For any $\gamma < 1$, we give a family of $\gamma$-weakly submodular functions and a simple partition matroid constraint and show that the standard greedy algorithm provides no constant approximation for the resulting constrained maximization problem.

Algebraic combinatorics often seeks bijections that explain identities between distributions object by object. Encoding combinatorial objects as words lets automata theory study such a bijection as a word-to-word computation and measure its memory, input access, and control of output order. This refines existence questions by asking which computational mechanisms a bijection requires. We develop this viewpoint for Dyck paths. Our motivating example is the $q,t$-Catalan polynomial. Let $D_n$ be the set of Dyck paths of semilength $n$, let $D=\bigcup_{n\ge 0}D_n$, and let $area, dinv, bounce \colon D\to\mathbb{N}$ be the standard statistics. Then, \[ C_n(q,t)=\sum_{P\in D_n}q^{area(P)}t^{bounce(P)} =\sum_{P\in D_n}q^{dinv(P)}t^{area(P)}. \] Haglund's zeta map $\zeta\colon D\to D$ gives a bijective proof: it preserves semilength and sends $(dinv,area)$ to $(area,bounce)$. By contrast, the full symmetry $C_n(q,t)=C_n(t,q)$ still lacks a direct explanation: no explicit, uniform, semilength-preserving bijection is known that swaps area and dinv on every Dyck path. Polyregular maps from automata theory provide a natural computational starting point, but we prove that neither $\zeta$ nor the classical height-sweep bijection witnessing Narayana symmetry is polyregular. The missing mechanism is global ordering by numerical levels whose range grows with the input. We call this a rank sort and introduce weighted-rank polyregular maps (WRP), extending polyregular maps by one such sort and containing both bijections. Nevertheless, WRP is a proper subclass of deterministic logspace. We prove that $\zeta^{-1}$ lies outside WRP and that no WRP map can realise a semilength-preserving area-dinv swap. Thus the rank-sorting strategy behind $\zeta$ cannot be extended within WRP to exchange the two statistics.

We consider the sequences of natural integers that can be computed by a deterministic transducer, with input in a structure A, output in N. and with memory the set of stacks of stacks of A. We show that these sequences are, exactly, the counting sequences of formal languages generated by unambiguous context-free indexed grammars (equivalently, the counting sequences of derivation trees of arbitrary context-free indexed grammars), with indexes in A. This general theorem applies, notably, to the set of natural integers endowed with the operation -1 and the non-zero predicate, showing that the polynomial recurrences count exactly the index-languages (where the parameter used for counting is the index itself).